Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 162176
    Prev
    Next
    INDEX
    Explanations

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tas
    -0.31
     getCount
    -0.29
     dataArray
    -0.26
    æ¶§
    -0.26
    sdale
    -0.25
     sÅĤow
    -0.24
     OMAP
    -0.24
    gren
    -0.24
    åĽ½å®ī
    -0.23
    iped
    -0.23
    POSITIVE LOGITS
    оÑĩки
    0.27
    ĴĮ
    0.26
     imm
    0.25
    åĴİ
    0.25
    isman
    0.25
    üm
    0.25
     gradu
    0.24
     prof
    0.24
    legg
    0.24
     cal
    0.24
    Activations Density 0.266%

    No Known Activations